[MODEL] New model support for kakaocorp/kanana-1.5-v-3b-instruct (#29384)

Signed-off-by: Jaehyun An <steve.ai@kakaocorp.com>

docs/models/supported_models.md

@@ -680,6 +680,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
 | `InternS1ForConditionalGeneration` | Intern-S1 | T + I<sup>E+</sup> + V<sup>E+</sup> | `internlm/Intern-S1`, `internlm/Intern-S1-mini`, etc. | ✅︎ | ✅︎ |
 | `InternVLChatModel` | InternVL 3.5, InternVL 3.0, InternVideo 2.5, InternVL 2.5, Mono-InternVL, InternVL 2.0 | T + I<sup>E+</sup> + (V<sup>E+</sup>) | `OpenGVLab/InternVL3_5-14B`, `OpenGVLab/InternVL3-9B`, `OpenGVLab/InternVideo2_5_Chat_8B`, `OpenGVLab/InternVL2_5-4B`, `OpenGVLab/Mono-InternVL-2B`, `OpenGVLab/InternVL2-4B`, etc. | ✅︎ | ✅︎ |
 | `InternVLForConditionalGeneration` | InternVL 3.0 (HF format) | T + I<sup>E+</sup> + V<sup>E+</sup> | `OpenGVLab/InternVL3-1B-hf`, etc. | ✅︎ | ✅︎ |
+| `KananaVForConditionalGeneration` | Kanana-V | T + I<sup>+</sup> | `kakaocorp/kanana-1.5-v-3b-instruct`, etc. | | ✅︎ |
 | `KeyeForConditionalGeneration` | Keye-VL-8B-Preview | T + I<sup>E+</sup> + V<sup>E+</sup> | `Kwai-Keye/Keye-VL-8B-Preview` | ✅︎ | ✅︎ |
 | `KeyeVL1_5ForConditionalGeneration` | Keye-VL-1_5-8B | T + I<sup>E+</sup> + V<sup>E+</sup> | `Kwai-Keye/Keye-VL-1_5-8B` | ✅︎ | ✅︎ |
 | `KimiVLForConditionalGeneration` | Kimi-VL-A3B-Instruct, Kimi-VL-A3B-Thinking | T + I<sup>+</sup> | `moonshotai/Kimi-VL-A3B-Instruct`, `moonshotai/Kimi-VL-A3B-Thinking` | | ✅︎ |

examples/offline_inference/vision_language.py

@@ -769,6 +769,33 @@ def run_internvl(questions: list[str], modality: str) -> ModelRequestData:
     )
 
 
+# Kanana-V
+def run_kanana_v(questions: list[str], modality: str) -> ModelRequestData:
+    assert modality == "image"
+
+    model_name = "kakaocorp/kanana-1.5-v-3b-instruct"
+
+    engine_args = EngineArgs(
+        model=model_name,
+        max_model_len=8192,
+        trust_remote_code=True,
+        limit_mm_per_prompt={modality: 1},
+    )
+
+    tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+    messages = [
+        [{"role": "user", "content": f"<image>\n{question}"}] for question in questions
+    ]
+    prompts = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+    return ModelRequestData(
+        engine_args=engine_args,
+        prompts=prompts,
+    )
+
+
 # Keye-VL
 def run_keye_vl(questions: list[str], modality: str) -> ModelRequestData:
     model_name = "Kwai-Keye/Keye-VL-8B-Preview"
@@ -1876,6 +1903,7 @@ model_example_map = {
     "idefics3": run_idefics3,
     "interns1": run_interns1,
     "internvl_chat": run_internvl,
+    "kanana_v": run_kanana_v,
     "keye_vl": run_keye_vl,
     "keye_vl1_5": run_keye_vl1_5,
     "kimi_vl": run_kimi_vl,

tests/models/registry.py

@@ -728,6 +728,10 @@ _MULTIMODAL_EXAMPLE_MODELS = {
         trust_remote_code=True,
     ),
     "InternVLForConditionalGeneration": _HfExamplesInfo("OpenGVLab/InternVL3-1B-hf"),
+    "KananaVForConditionalGeneration": _HfExamplesInfo(
+        "kakaocorp/kanana-1.5-v-3b-instruct",
+        trust_remote_code=True,
+    ),
     "KeyeForConditionalGeneration": _HfExamplesInfo(
         "Kwai-Keye/Keye-VL-8B-Preview",
         trust_remote_code=True,

vllm/model_executor/models/registry.py

@@ -343,6 +343,7 @@ _MULTIMODAL_MODELS = {
     ),
     "IsaacForConditionalGeneration": ("isaac", "IsaacForConditionalGeneration"),
     "SmolVLMForConditionalGeneration": ("smolvlm", "SmolVLMForConditionalGeneration"),  # noqa: E501
+    "KananaVForConditionalGeneration": ("kanana_v", "KananaVForConditionalGeneration"),
     "KeyeForConditionalGeneration": ("keye", "KeyeForConditionalGeneration"),
     "KeyeVL1_5ForConditionalGeneration": (
         "keye_vl1_5",